olmo2-1b-sft-variant-R1

Research artifacts: OLMo-2-1B training variants produced under controlled data-composition differences; per-seed subfolders; intended for reproducibility and membership/contamination research. Details and provenance will be documented in a future update.

Subfolders

seed20260820
seed20260821
seed20260822
seed20260823
seed20260824
seed20260825
seed20260826
seed20260827
seed20260828
seed20260829

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "XUUUUSID/olmo2-1b-sft-variant-R1"
sub = "seed20260820"
tok = AutoTokenizer.from_pretrained(repo, subfolder=sub)
model = AutoModelForCausalLM.from_pretrained(repo, subfolder=sub)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support